Lune Research

by luneresearch.com MCP server, indexed and not reviewed

HostedLocalvendor's own

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

Search peer-reviewed papers and research methodology guidance from your AI agent.

What the official MCP registry says

Facts

MCP registry
com.luneresearch/lune · 3.0.1
Endpoint
https://mcp.luneresearch.com
Packages
npm @retrograde-labs/lune-mcp-server stdio
npm / week
147
GitHub stars
4
Registry entry
updated 5 Nov 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under luneresearch.com, a namespace the registry only gives to whoever proves they control that domain.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 13 · about 13,138 tokens of context · checked 19 hours ago

ToolWhat it doesHint
search_papersSearch paperswithheldread-only
search_papers_manySearch papers (multi-query)withheldread-only
get_paper_fulltextGet paper full textwithheldread-only
get_paper_citationsGet paper citationswithheldread-only
list_conferencesList conferenceswithheldread-only
get_conference_papersGet conference paperswithheldread-only
search_related_papersSearch related paperswithheldread-only
extract_from_papersExtract structured fields from paperswithheldread-only
verify_claimsVerify claims against the corpuswithheldread-only
gather_evidenceGather evidence and judge sufficiencywithheldread-only
search_research_guidanceSearch research guidancewithheldread-only
get_research_guidance_docGet research guidance documentwithheldread-only
send_feedbackSend feedback to Lunewithheldwrites

What https://mcp.luneresearch.com answered to tools/list, asked without credentials over MCP 2026-07-28. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 1 error · 11 warnings · 1 note

Its tool definitions contain text aimed at the model (TC19), which is how tool poisoning is written, so this site doesn't repeat them. An agent shouldn't connect to it without its user's say-so.

  • errorTC19search_papersthe definition tells the model to keep something from the user
  • warnTC10gather_evidence"max_iterations" is required and has a default
  • warnTC10search_papers_many"limit" is required and has a default
  • warnTC10search_papers_many"detail" is required and has a default
  • warnTC11gather_evidence3 parameters without a description: year, year_max, year_min
  • warnTC11search_papers2 parameters without a description: limit, year
  • warnTC11search_related_papers1 parameter without a description: limit
  • warnTC11search_research_guidancenone of its 2 parameters has a description
  • warnTC14list_conferencesallowed values are in the description, not an enum: category
  • warnTC22gather_evidencethe definition is about 1,816 tokens
  • warnTC22search_papersthe definition is about 2,167 tokens
  • warnTC22search_papers_manythe definition is about 2,272 tokens
  • noteTC24server1 of 13 tools have no outputSchema

The checks from /check and anchor check, run each day on the list above: about 13,138 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.